Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 944 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.8156. Min Act: -0.0000

Data Index: 1213965 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.7182. Min Act: -0.0000

Data Index: 9765 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.8832. Min Act: -0.0000

Data Index: 920379 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.7245. Min Act: -0.0000

Data Index: 750366 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.7727. Min Act: -0.0000

Data Index: 1166261 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.7280. Min Act: -0.0000

Data Index: 87219 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.6842. Min Act: -0.0000

Data Index: 776377 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.6605. Min Act: -0.0000

Data Index: 1274630 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.6989. Min Act: -0.0000

Data Index: 890058 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.5372. Min Act: -0.0000

Data Index: 361171 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.5643. Min Act: -0.0000

Data Index: 755999 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.5193. Min Act: -0.0000

Data Index: 425477 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.5184. Min Act: -0.0000

Data Index: 1312905 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.5238. Min Act: -0.0000

Data Index: 837644 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.5590. Min Act: -0.0000

Data Index: 173653 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.5577. Min Act: -0.0000

Data Index: 238288 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.5358. Min Act: -0.0000

Data Index: 1295035 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.5198. Min Act: -0.0000

Data Index: 235745 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.4900. Min Act: -0.0000

Data Index: 1140023 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 1.8832. Min Range: -1.8832

Max Act: 1.5167. Min Act: -0.0000

Data Index: 1274515 (C4 (Web Text))

Max Activating Token Index: 1009